{"ID":2836189,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.20989","arxiv_id":"2511.20989","title":"RefOnce: Distilling References into a Prototype Memory for Referring Camouflaged Object Detection","abstract":"Referring Camouflaged Object Detection (Ref-COD) segments specified camouflaged objects in a scene by leveraging a small set of referring images. Though effective, current systems adopt a dual-branch design that requires reference images at test time, which limits deployability and adds latency and data-collection burden. We introduce a Ref-COD framework that distills references into a class-prototype memory during training and synthesizes a reference vector at inference via a query-conditioned mixture of prototypes. Concretely, we maintain an EMA-updated prototype per category and predict mixture weights from the query to produce a guidance vector without any test-time references. To bridge the representation gap between reference statistics and camouflaged query features, we propose a bidirectional attention alignment module that adapts both the query features and the class representation. Thus, our approach yields a simple, efficient path to Ref-COD without mandatory references. We evaluate the proposed method on the large-scale R2C7K benchmark. Extensive experiments demonstrate competitive or superior performance of the proposed method compared with recent state-of-the-arts. Code is available at https://github.com/yuhuan-wu/RefOnce.","short_abstract":"Referring Camouflaged Object Detection (Ref-COD) segments specified camouflaged objects in a scene by leveraging a small set of referring images. Though effective, current systems adopt a dual-branch design that requires reference images at test time, which limits deployability and adds latency and data-collection burd...","url_abs":"https://arxiv.org/abs/2511.20989","url_pdf":"https://arxiv.org/pdf/2511.20989v1","authors":"[\"Yu-Huan Wu\",\"Zi-Xuan Zhu\",\"Yan Wang\",\"Liangli Zhen\",\"Deng-Ping Fan\"]","published":"2025-11-26T02:42:52Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":606576,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2836189,"paper_url":"https://arxiv.org/abs/2511.20989","paper_title":"RefOnce: Distilling References into a Prototype Memory for Referring Camouflaged Object Detection","repo_url":"https://github.com/yuhuan-wu/RefOnce","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}